public static void ExampleProteinGrouping(IProtease protease, double percentIdentified = 0.01, int maxMissed = 3, int minLength = 5, int maxLength = 50)
{
Stopwatch watch = new Stopwatch();
watch.Start();
List<Peptide> peps = new List<Peptide>(1000000);
List<Protein> proteins = new List<Protein>(7000);
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
peps.AddRange(protein.Digest(protease, maxMissed, minLength, maxLength));
proteins.Add(protein);
}
}
Console.WriteLine("Loaded {0:N0} peptides from {1:N0} proteins in {2} ms", peps.Count, proteins.Count, watch.ElapsedMilliseconds);
watch.Restart();
Random random = new Random(480912341);
// Take the first x % to act as our identified peptides
List<Peptide> identifiedPeptides = peps.OrderBy(x => random.Next()).Take((int) (peps.Count*percentIdentified)).ToList();
List<ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} protein groups from {2:N0} identified sequences", proteins.Count, proteinGroups.Count, identifiedPeptides.Count);
Console.WriteLine();
Console.WriteLine("Time elapsed: {0} ms", watch.ElapsedMilliseconds);
}
public static void Start(IProtease protease, double percentIdentified = 0.05, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
Console.WriteLine("**Start Protein Grouping**");
Stopwatch watch = new Stopwatch();
watch.Start();
List<Peptide> peps = new List<Peptide>();
List<Protein> proteins = new List<Protein>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
}
proteins.Add(protein);
}
}
Console.WriteLine("Loaded {0:N0} peptides from {1:N0} proteins in {2} ms", peps.Count, proteins.Count, watch.ElapsedMilliseconds);
// Fixed seed to make it reproducible
Random random = new Random(480912341);
// Take the first x % to act as our identified peptides
List<Peptide> identifiedPeptides = peps.OrderBy(x => random.Next()).Take((int) (peps.Count*percentIdentified)).ToList();
List<ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} protein groups from {2:N0} identified sequences", proteins.Count, proteinGroups.Count, identifiedPeptides.Count);
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", System.Environment.WorkingSet/(1024*1024));
Console.WriteLine("**END Protein Grouping**");
}
public static IEnumerable <ProteinGroup> GroupProteins(string fastaFile, IProtease protease, IEnumerable <IAminoAcidSequence> observeredSequences, IEqualityComparer <IAminoAcidSequence> peptideComparer, int MaxMissedCleavages = 3)
{
using (FastaReader fasta = new FastaReader(fastaFile))
{
return(GroupProteins(fasta.ReadNextProtein(), new[] { protease }, observeredSequences, peptideComparer, MaxMissedCleavages));
}
}
public static void Start(IProtease protease, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
Console.WriteLine("**Start Morpheus Search**");
Stopwatch watch = new Stopwatch();
watch.Start();
List<int> hashCodes = new List<int>();
// Generate peptide candidates
HashSet<Peptide> peptides = new HashSet<Peptide>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peptides.Add(peptide);
}
}
}
MSSearchEngine engine = new MorpheusSearchEngine();
engine.PrecursorMassTolerance = Tolerance.FromPPM(100);
engine.ProductMassTolerance = Tolerance.FromPPM(10);
engine.LoadPeptides(peptides);
watch.Stop();
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", Environment.WorkingSet/(1024*1024));
Console.WriteLine("**End Morpheus Search**");
}
public static void Start(IProtease protease, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
Console.WriteLine("**Start Morpheus Search**");
Stopwatch watch = new Stopwatch();
watch.Start();
List <int> hashCodes = new List <int>();
// Generate peptide candidates
HashSet <Peptide> peptides = new HashSet <Peptide>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peptides.Add(peptide);
}
}
}
MSSearchEngine engine = new MorpheusSearchEngine();
engine.PrecursorMassTolerance = Tolerance.FromPPM(100);
engine.ProductMassTolerance = Tolerance.FromPPM(10);
engine.LoadPeptides(peptides);
watch.Stop();
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**End Morpheus Search**");
}
public static void Start(IProtease protease, int maxMissed = 1, int minLength = 0, int maxLength = int.MaxValue, bool storeSequenceString = true)
{
Console.WriteLine("**Start Digestion**");
Stopwatch watch = new Stopwatch();
watch.Start();
List <Peptide> peps = new List <Peptide>();
List <Protein> prots = new List <Protein>();
List <double> allMzs = new List <double>();
AminoAcidPolymer.StoreSequenceString = storeSequenceString;
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
allMzs.Add(peptide.ToMz(2)); // forces the calculation of the mass and thus chemical formula
}
prots.Add(protein);
}
}
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} peptides using {2:N0} missed cleavages", prots.Count, peps.Count, maxMissed);
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**End Digestion**");
}
public static void StartRamp(IProtease protease, double percentIdentifiedSteps = 0.05, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
List <Peptide> peps = new List <Peptide>();
List <Protein> proteins = new List <Protein>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
}
proteins.Add(protein);
}
}
// Fixed seed to make it reproducible
Random random = new Random(480912341);
peps = peps.OrderBy(x => random.Next()).ToList();
for (double percentIdentified = 0; percentIdentified <= 1; percentIdentified += percentIdentifiedSteps)
{
// Take the first x % to act as our identified peptides
List <Peptide> identifiedPeptides = peps.Take((int)(peps.Count * percentIdentified)).ToList();
List <ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
Console.WriteLine("{0} peptides {1} protein groups", identifiedPeptides.Count, proteinGroups.Count);
}
}
public static void Start(IProtease protease, int maxMissed = 1, int minLength = 0, int maxLength = int.MaxValue, bool storeSequenceString = true)
{
Console.WriteLine("**Start Digestion**");
Stopwatch watch = new Stopwatch();
watch.Start();
List<Peptide> peps = new List<Peptide>();
List<Protein> prots = new List<Protein>();
List<double> allMzs = new List<double>();
AminoAcidPolymer.StoreSequenceString = storeSequenceString;
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
allMzs.Add(peptide.ToMz(2)); // forces the calculation of the mass and thus chemical formula
}
prots.Add(protein);
}
}
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} peptides using {2:N0} missed cleavages", prots.Count, peps.Count, maxMissed);
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", System.Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**End Digestion**");
}
public static void ExampleDigestion()
{
const string fastaFilePath = "Resources/yeast_uniprot_120226.fasta";
IProtease trypsin = Protease.GetProtease("Trypsin");
const int maxMissedCleavages = 3;
const int minPeptideLength = 5;
const int maxPeptideLength = 50;
List <double> masses = new List <double>();
Stopwatch watch = new Stopwatch();
watch.Start();
using (FastaReader reader = new FastaReader(fastaFilePath))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(trypsin, maxMissedCleavages, minPeptideLength, maxPeptideLength))
{
masses.Add(peptide.MonoisotopicMass);
}
}
}
//Console.WriteLine("Average Peptide Mass = {0:F4}", masses.Average());
watch.Stop();
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
}
public static void Start(IProtease protease, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
//Console.WriteLine("**Start Protein Grouping**");
//Stopwatch watch = new Stopwatch();
//watch.Start();
//List<Peptide> peps = new List<Peptide>();
//List<Protein> prots = new List<Protein>();
//using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
//{
// foreach (Protein protein in reader.ReadNextProtein())
// {
// foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
// {
// peps.Add(peptide);
// }
// prots.Add(protein);
// }
//}
//List<ProteinGroup> groups = new List<ProteinGroup>();
//ProteinGroup.SetProteins(prots, protease, maxMissed, minLength, maxLength);
//foreach (Peptide pep in peps)
//{
// ProteinGroup pg = ProteinGroup.Group(pep);
// groups.Add(pg);
//}
//watch.Stop();
//Console.WriteLine("{0:N0} proteins produced {1:N0} protein groups using {2:N0} missed clevages", prots.Count, groups.Count, maxMissed);
//Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
//Console.WriteLine("Memory used: {0:N0} MB", System.Environment.WorkingSet / (1024 * 1024));
//Console.WriteLine("**End Digestion**");
}
public static void ExampleProteinGrouping(IProtease protease, double percentIdentified = 0.01, int maxMissed = 3, int minLength = 5, int maxLength = 50)
{
Stopwatch watch = new Stopwatch();
watch.Start();
List <Peptide> peps = new List <Peptide>(1000000);
List <Protein> proteins = new List <Protein>(7000);
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
peps.AddRange(protein.Digest(protease, maxMissed, minLength, maxLength));
proteins.Add(protein);
}
}
Console.WriteLine("Loaded {0:N0} peptides from {1:N0} proteins in {2} ms", peps.Count, proteins.Count, watch.ElapsedMilliseconds);
watch.Restart();
Random random = new Random(480912341);
// Take the first x % to act as our identified peptides
List <Peptide> identifiedPeptides = peps.OrderBy(x => random.Next()).Take((int)(peps.Count * percentIdentified)).ToList();
List <ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} protein groups from {2:N0} identified sequences", proteins.Count, proteinGroups.Count, identifiedPeptides.Count);
Console.WriteLine();
Console.WriteLine("Time elapsed: {0} ms", watch.ElapsedMilliseconds);
}
private void btnDigest_Click(object sender, EventArgs e)
{
String enzymeName = lbxDigestion.SelectedItem.ToString();
IProtease protease = Enzymes.AllEnzymes()[enzymeName];
String organism = lbxOrganisms.SelectedItem.ToString();
RunBackground(() =>
proteomeDb.GetOrganism(organism).Digest(protease, enzymeName, null, UpdateProgress));
}
public static void AssignNumProteaseTermini(this IProtease protease, IIdentifiedSpectrum s)
{
var counts = (from p in s.Peptides
let beforeChar = p.Sequence[0]
let afterChar = p.Sequence[p.Sequence.Length - 1]
let c = protease.GetProteaseTerminiCount(beforeChar, p.PureSequence, afterChar, '-')
select c).Distinct().ToList();
s.NumProteaseTermini = counts.Max();
}
public ProteinMatchSettings(ProteomeDbPath proteomeDbPath, IProtease protease, ProteinMatchType proteinMatchTypes, String searchText)
{
ProteomeDbPath = proteomeDbPath;
Protease = protease;
if (protease != null)
{
using (var proteomeDb = proteomeDbPath.OpenProteomeDb())
{
Digestion = proteomeDb.GetDigestion(protease.Name);
}
}
MatchTypes = proteinMatchTypes;
SearchText = searchText;
}
public ProteinMatchSettings(ProteomeDbPath proteomeDbPath, IProtease protease, ProteinMatchType proteinMatchTypes, String searchText)
{
ProteomeDbPath = proteomeDbPath;
Protease = protease;
if (protease != null)
{
using (var proteomeDb = proteomeDbPath.OpenProteomeDb())
{
Digestion = proteomeDb.GetDigestion(protease.Name);
}
}
MatchTypes = proteinMatchTypes;
SearchText = searchText;
}
public static int GetNumProteaseTermini(this IProtease protease, char beforeChar, string pureSeq, char afterChar, char terminalChar, int positionInProtein)
{
int result = 0;
if (beforeChar == 'M' && positionInProtein == 2)
{
result++;
}
else if (protease.IsCleavageSite(beforeChar, pureSeq[0], terminalChar))
{
result++;
}
if (protease.IsCleavageSite(pureSeq[pureSeq.Length - 1], afterChar, terminalChar))
{
result++;
}
return(result);
}
public static void Start(IProtease protease, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
Console.WriteLine("**Start Morpheus Search**");
Stopwatch watch = new Stopwatch();
watch.Start();
List<int> hashCodes = new List<int>();
// Generate peptide candidates
HashSet<Peptide> peptides = new HashSet<Peptide>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peptides.Add(peptide);
}
}
}
MSSearchEngine engine = new MorpheusSearchEngine();
engine.PrecursorMassTolerance = Tolerance.FromPPM(100);
engine.ProductMassTolerance = Tolerance.FromPPM(10);
engine.LoadPeptides(peptides);
using (MSDataFile msDataFile = new ThermoRawFile("Resources/ThermoRawFileMS1MS2.raw"))
{
//SortedMaxSizedContainer<PeptideSpectralMatch> psms = engine.Search(msDataFile.Where(scan => scan.MsnOrder > 1));
//foreach (MSDataScan scan in msDataFile.Where(scan => scan.MsnOrder > 1))
//{
// List<PeptideSpectralMatch> psms = engine.Search(scan);
// Console.WriteLine("{0} {1}", scan.SpectrumNumber, psms.Count);
//}
}
watch.Stop();
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", System.Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**End Morpheus Search**");
}
public static void Start(IProtease protease, double percentIdentified = 0.05, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
Console.WriteLine("**Start Protein Grouping**");
Stopwatch watch = new Stopwatch();
watch.Start();
List <Peptide> peps = new List <Peptide>();
List <Protein> proteins = new List <Protein>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
}
proteins.Add(protein);
}
}
Console.WriteLine("Loaded {0:N0} peptides from {1:N0} proteins in {2} ms", peps.Count, proteins.Count, watch.ElapsedMilliseconds);
// Fixed seed to make it reproducible
Random random = new Random(480912341);
// Take the first x % to act as our identified peptides
List <Peptide> identifiedPeptides = peps.OrderBy(x => random.Next()).Take((int)(peps.Count * percentIdentified)).ToList();
List <ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} protein groups from {2:N0} identified sequences", proteins.Count, proteinGroups.Count, identifiedPeptides.Count);
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", System.Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**END Protein Grouping**");
}
public static IEnumerable <ProteinGroup> GroupProteins(IEnumerable <Protein> proteins, IProtease protease, IEnumerable <IAminoAcidSequence> observeredSequences, IEqualityComparer <IAminoAcidSequence> peptideComparer, int MaxMissedCleavages = 3, int minPepPerProtein = 1)
{
return(GroupProteins(proteins, new[] { protease }, observeredSequences, peptideComparer, MaxMissedCleavages));
}
/// <summary>
/// Digests this protein into peptides.
/// </summary>
/// <param name="protease">The protease to digest with</param>
/// <param name="maxMissedCleavages">The max number of missed cleavages generated, 0 means no missed cleavages</param>
/// <param name="minLength">The minimum length (in amino acids) of the peptide</param>
/// <param name="maxLength">The maximum length (in amino acids) of the peptide</param>
/// <param name="initiatorMethonine"></param>
/// <param name="includeModifications"></param>
/// <param name="semiDigestion"></param>
/// <returns>A list of digested peptides</returns>
public virtual IEnumerable <Peptide> Digest(IProtease protease, int maxMissedCleavages = 3, int minLength = 1, int maxLength = int.MaxValue, bool initiatorMethonine = true, bool includeModifications = false, bool semiDigestion = false)
{
return(Digest(new[] { protease }, maxMissedCleavages, minLength, maxLength, initiatorMethonine, includeModifications, semiDigestion));
}
public static IEnumerable <string> Digest(AminoAcidPolymer polymer, IProtease protease, int maxMissedCleavages, int minLength, int maxLength, bool methionineInitiator, bool semiDigestion)
{
return(Digest(polymer.BaseSequence, new[] { protease }, maxMissedCleavages, minLength, maxLength, methionineInitiator, semiDigestion));
}
public static IEnumerable <string> Digest(AminoAcidPolymer sequence, IProtease protease)
{
return(Digest(sequence, protease, 3, 1, int.MaxValue, true, false));
}
public Digestion Digest(IProtease protease, String name, String description, ProgressMonitor progressMonitor)
{
DbOrganism organism;
DbDigestion digestion;
List <DbProtein> proteins;
using (ISession session = ProteomeDb.OpenWriteSession())
{
organism = GetEntity(session);
session.BeginTransaction();
digestion = new DbDigestion
{
Name = name,
Description = description,
Organism = organism,
MaxMissedCleavages = protease.MaxMissedCleavages
};
session.Save(digestion);
if (!progressMonitor.Invoke("Listing proteins", 0))
{
return(null);
}
proteins = new List <DbProtein>(organism.Proteins);
Dictionary <String, long> digestedPeptideIds
= new Dictionary <string, long>();
const String sqlPeptide =
"INSERT INTO ProteomeDbDigestedPeptide (Digestion, MissedCleavages, Sequence, Version) VALUES(@Digestion,@MissedCleavages,@Sequence,1);select last_insert_rowid();";
var commandPeptide = session.Connection.CreateCommand();
commandPeptide.CommandText = sqlPeptide;
commandPeptide.Parameters.Add(new SQLiteParameter("@Digestion"));
commandPeptide.Parameters.Add(new SQLiteParameter("@MissedCleavages"));
commandPeptide.Parameters.Add(new SQLiteParameter("@Sequence"));
const String sqlPeptideProtein =
"INSERT INTO ProteomeDbDigestedPeptideProtein (StartIndex, Peptide, Protein, Version) VALUES(?,?,?,1);";
var commandProtein = session.Connection.CreateCommand();
commandProtein.CommandText = sqlPeptideProtein;
commandProtein.Parameters.Add(new SQLiteParameter("@StartIndex"));
commandProtein.Parameters.Add(new SQLiteParameter("@Peptide"));
commandProtein.Parameters.Add(new SQLiteParameter("@Protein"));
for (int i = 0; i < proteins.Count; i++)
{
if (!progressMonitor.Invoke("Digesting " + proteins.Count
+ " proteins", 100 * i / proteins.Count))
{
return(null);
}
Protein protein = new Protein(this, proteins[i]);
foreach (DigestedPeptide digestedPeptide in protease.Digest(protein))
{
if (digestedPeptide.Sequence.Length > MAX_PEPTIDE_LENGTH)
{
continue;
}
long digestedPeptideId;
if (!digestedPeptideIds.TryGetValue(digestedPeptide.Sequence, out digestedPeptideId))
{
((SQLiteParameter)commandPeptide.Parameters[0]).Value = digestion.Id;
((SQLiteParameter)commandPeptide.Parameters[1]).Value = digestedPeptide.MissedCleavages;
((SQLiteParameter)commandPeptide.Parameters[2]).Value = digestedPeptide.Sequence;
digestedPeptideId = Convert.ToInt64(commandPeptide.ExecuteScalar());
digestedPeptideIds.Add(digestedPeptide.Sequence, digestedPeptideId);
}
((SQLiteParameter)commandProtein.Parameters[0]).Value = digestedPeptide.Index;
((SQLiteParameter)commandProtein.Parameters[1]).Value = digestedPeptideId;
((SQLiteParameter)commandProtein.Parameters[2]).Value = proteins[i].Id;
commandProtein.ExecuteNonQuery();
}
}
if (!progressMonitor.Invoke("Committing transaction", 99))
{
return(null);
}
session.Transaction.Commit();
progressMonitor.Invoke(
"Digested " + proteins.Count + " proteins into " + digestedPeptideIds.Count + " unique peptides",
100);
return(new Digestion(this, digestion));
}
}
/// <summary>
/// Digests this protein into peptides.
/// </summary>
/// <param name="protease">The protease to digest with</param>
/// <param name="maxMissedCleavages">The max number of missed cleavages generated, 0 means no missed cleavages</param>
/// <param name="minLength">The minimum length (in amino acids) of the peptide</param>
/// <param name="maxLength">The maximum length (in amino acids) of the peptide</param>
/// <param name="initiatorMethonine"></param>
/// <param name="includeModifications"></param>
/// <param name="semiDigestion"></param>
/// <returns>A list of digested peptides</returns>
public virtual IEnumerable<Peptide> Digest(IProtease protease, int maxMissedCleavages = 3, int minLength = 1, int maxLength = int.MaxValue, bool initiatorMethonine = true, bool includeModifications = false, bool semiDigestion = false)
{
return Digest(new[] {protease}, maxMissedCleavages, minLength, maxLength, initiatorMethonine, includeModifications, semiDigestion);
}
public Digestion Digest(IProtease protease, ProgressMonitor progressMonitor)
{
using (ISession session = OpenWriteSession())
{
DbDigestion dbDigestion = GetDbDigestion(protease.Name);
HashSet <string> existingSequences = new HashSet <string>();
using (var transaction = session.BeginTransaction())
{
if (dbDigestion != null)
{
if (dbDigestion.MaxSequenceLength >= MAX_SEQUENCE_LENGTH)
{
return(new Digestion(this, dbDigestion));
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_Digest_Listing_existing_peptides, 0))
{
return(null);
}
IQuery query = session.CreateQuery("SELECT P.Sequence FROM " // Not L10N
+ typeof(DbDigestedPeptide) + " P WHERE P.Digestion = :Digestion") // Not L10N
.SetParameter("Digestion", dbDigestion); // Not L10N
List <String> listSequences = new List <string>();
query.List(listSequences);
existingSequences.UnionWith(listSequences);
dbDigestion.MaxSequenceLength = MAX_SEQUENCE_LENGTH;
session.Update(dbDigestion);
}
else
{
dbDigestion = new DbDigestion
{
Name = protease.Name,
MinSequenceLength = MIN_SEQUENCE_LENGTH,
MaxSequenceLength = MAX_SEQUENCE_LENGTH,
};
session.Save(dbDigestion);
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_Digest_Listing_proteins, 0))
{
return(null);
}
List <DbProtein> proteins = new List <DbProtein>();
session.CreateCriteria(typeof(DbProtein)).List(proteins);
Dictionary <String, long> digestedPeptideIds
= new Dictionary <string, long>();
const String sqlPeptide =
"INSERT INTO ProteomeDbDigestedPeptide (Digestion, Sequence) VALUES(?,?);select last_insert_rowid();"; // Not L10N
using (var commandPeptide = session.Connection.CreateCommand())
using (var commandProtein = session.Connection.CreateCommand())
{
commandPeptide.CommandText = sqlPeptide;
commandPeptide.Parameters.Add(new SQLiteParameter());
commandPeptide.Parameters.Add(new SQLiteParameter());
const String sqlPeptideProtein =
"INSERT INTO ProteomeDbDigestedPeptideProtein (Peptide, Protein) VALUES(?,?);"; // Not L10N
commandProtein.CommandText = sqlPeptideProtein;
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
for (int i = 0; i < proteins.Count; i++)
{
var proteinSequences = new HashSet <string>();
if (!progressMonitor.Invoke(string.Format(Resources.ProteomeDb_Digest_Digesting__0__proteins, proteins.Count), 100 * i / proteins.Count))
{
return(null);
}
Protein protein = new Protein(ProteomeDbPath, proteins[i]);
foreach (DigestedPeptide digestedPeptide in protease.Digest(protein))
{
if (digestedPeptide.Sequence.Length < dbDigestion.MinSequenceLength)
{
continue;
}
String truncatedSequence = digestedPeptide.Sequence.Substring(
0, Math.Min(digestedPeptide.Sequence.Length, dbDigestion.MaxSequenceLength));
if (existingSequences.Contains(truncatedSequence))
{
continue;
}
if (proteinSequences.Contains(truncatedSequence))
{
continue;
}
proteinSequences.Add(truncatedSequence);
long digestedPeptideId;
if (!digestedPeptideIds.TryGetValue(truncatedSequence, out digestedPeptideId))
{
((SQLiteParameter)commandPeptide.Parameters[0]).Value = dbDigestion.Id;
((SQLiteParameter)commandPeptide.Parameters[1]).Value = truncatedSequence;
digestedPeptideId = Convert.ToInt64(commandPeptide.ExecuteScalar());
digestedPeptideIds.Add(truncatedSequence, digestedPeptideId);
}
((SQLiteParameter)commandProtein.Parameters[0]).Value = digestedPeptideId;
((SQLiteParameter)commandProtein.Parameters[1]).Value = protein.Id;
commandProtein.ExecuteNonQuery();
}
}
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_AddFastaFile_Saving_changes, 99))
{
return(null);
}
transaction.Commit();
AnalyzeDb(session);
progressMonitor.Invoke(
string.Format(Resources.ProteomeDb_Digest_Digested__0__proteins_into__1__unique_peptides,
proteins.Count, digestedPeptideIds.Count),
100);
}
return(new Digestion(this, dbDigestion));
}
}
public Digestion Digest(IProtease protease, ProgressMonitor progressMonitor)
{
using (ISession session = OpenWriteSession())
{
DbDigestion dbDigestion = GetDbDigestion(protease.Name);
HashSet<string> existingSequences = new HashSet<string>();
using (var transaction = session.BeginTransaction())
{
if (dbDigestion != null)
{
if (dbDigestion.MaxSequenceLength >= MAX_SEQUENCE_LENGTH)
{
return new Digestion(this, dbDigestion);
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_Digest_Listing_existing_peptides, 0))
{
return null;
}
IQuery query = session.CreateQuery("SELECT P.Sequence FROM " // Not L10N
+ typeof(DbDigestedPeptide) + " P WHERE P.Digestion = :Digestion") // Not L10N
.SetParameter("Digestion", dbDigestion); // Not L10N
List<String> listSequences = new List<string>();
query.List(listSequences);
existingSequences.UnionWith(listSequences);
dbDigestion.MaxSequenceLength = MAX_SEQUENCE_LENGTH;
session.Update(dbDigestion);
}
else
{
dbDigestion = new DbDigestion
{
Name = protease.Name,
MinSequenceLength = MIN_SEQUENCE_LENGTH,
MaxSequenceLength = MAX_SEQUENCE_LENGTH,
};
session.Save(dbDigestion);
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_Digest_Listing_proteins, 0))
{
return null;
}
List<DbProtein> proteins = new List<DbProtein>();
session.CreateCriteria(typeof(DbProtein)).List(proteins);
Dictionary<String, long> digestedPeptideIds
= new Dictionary<string, long>();
const String sqlPeptide =
"INSERT INTO ProteomeDbDigestedPeptide (Digestion, Sequence) VALUES(?,?);select last_insert_rowid();"; // Not L10N
using (var commandPeptide = session.Connection.CreateCommand())
using (var commandProtein = session.Connection.CreateCommand())
{
commandPeptide.CommandText = sqlPeptide;
commandPeptide.Parameters.Add(new SQLiteParameter());
commandPeptide.Parameters.Add(new SQLiteParameter());
const String sqlPeptideProtein =
"INSERT INTO ProteomeDbDigestedPeptideProtein (Peptide, Protein) VALUES(?,?);"; // Not L10N
commandProtein.CommandText = sqlPeptideProtein;
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
for (int i = 0; i < proteins.Count; i++)
{
var proteinSequences = new HashSet<string>();
if (!progressMonitor.Invoke(string.Format(Resources.ProteomeDb_Digest_Digesting__0__proteins,proteins.Count), 100 * i / proteins.Count))
{
return null;
}
Protein protein = new Protein(ProteomeDbPath, proteins[i]);
foreach (DigestedPeptide digestedPeptide in protease.Digest(protein))
{
if (digestedPeptide.Sequence.Length < dbDigestion.MinSequenceLength)
{
continue;
}
String truncatedSequence = digestedPeptide.Sequence.Substring(
0, Math.Min(digestedPeptide.Sequence.Length, dbDigestion.MaxSequenceLength));
if (existingSequences.Contains(truncatedSequence))
{
continue;
}
if (proteinSequences.Contains(truncatedSequence))
{
continue;
}
proteinSequences.Add(truncatedSequence);
long digestedPeptideId;
if (!digestedPeptideIds.TryGetValue(truncatedSequence, out digestedPeptideId))
{
((SQLiteParameter)commandPeptide.Parameters[0]).Value = dbDigestion.Id;
((SQLiteParameter)commandPeptide.Parameters[1]).Value = truncatedSequence;
digestedPeptideId = Convert.ToInt64(commandPeptide.ExecuteScalar());
digestedPeptideIds.Add(truncatedSequence, digestedPeptideId);
}
((SQLiteParameter)commandProtein.Parameters[0]).Value = digestedPeptideId;
((SQLiteParameter)commandProtein.Parameters[1]).Value = protein.Id;
commandProtein.ExecuteNonQuery();
}
}
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_AddFastaFile_Saving_changes, 99))
{
return null;
}
transaction.Commit();
AnalyzeDb(session);
progressMonitor.Invoke(
string.Format(Resources.ProteomeDb_Digest_Digested__0__proteins_into__1__unique_peptides,
proteins.Count, digestedPeptideIds.Count),
100);
}
return new Digestion(this, dbDigestion);
}
}
public Digestion Digest(IProtease protease, int maxMissedCleavages, IProgressMonitor progressMonitor, ref IProgressStatus status, bool delayDbIndexing = false)
{
using (ISession session = OpenWriteSession())
{
DbDigestion dbDigestion = GetDbDigestion(protease.Name, session);
HashSet <string> existingSequences; // TODO(bspratt) - the logic around this seems fishy, investigate. Probably never actually been used. Part of fix for issue #304, probably
if (dbDigestion != null)
{
if (dbDigestion.MaxSequenceLength >= MAX_SEQUENCE_LENGTH)
{
return(new Digestion(this, dbDigestion));
}
if (!UpdateProgressAndCheckForCancellation(progressMonitor, ref status, Resources.ProteomeDb_Digest_Listing_existing_peptides, 0))
{
return(null);
}
IQuery query = session.CreateQuery("SELECT P.Sequence FROM " // Not L10N
+ typeof(DbDigestedPeptide) + " P WHERE P.Digestion = :Digestion") // Not L10N
.SetParameter("Digestion", dbDigestion); // Not L10N
List <String> listSequences = new List <string>();
query.List(listSequences);
existingSequences = new HashSet <string>(listSequences);
dbDigestion.MaxSequenceLength = MAX_SEQUENCE_LENGTH;
}
else
{
dbDigestion = new DbDigestion
{
Name = protease.Name,
MinSequenceLength = MIN_SEQUENCE_LENGTH,
MaxSequenceLength = MAX_SEQUENCE_LENGTH,
};
existingSequences = new HashSet <string>();
}
if (!UpdateProgressAndCheckForCancellation(progressMonitor, ref status, Resources.ProteomeDb_Digest_Listing_proteins, 0))
{
return(null);
}
var dbProteins = new List <DbProtein>();
session.CreateCriteria(typeof(DbProtein)).List(dbProteins);
// Digest the proteins
var proteinCount = dbProteins.Count;
if (proteinCount == 0)
{
return(null);
}
var proteinsList = new Protein[proteinCount];
var truncatedSequences = new HashSet <string> [proteinCount]; // One hashset of sequences for each protein of interest
const int N_DIGEST_THREADS = 16; // Arbitrary value - do a progress/canel check every nth protein
string message = string.Format(Resources.ProteomeDb_Digest_Digesting__0__proteins, proteinCount);
for (var i = 0; i < proteinCount; i += N_DIGEST_THREADS)
{
var endRange = Math.Min(proteinCount, i + N_DIGEST_THREADS);
if (!UpdateProgressAndCheckForCancellation(progressMonitor, ref status, message, 50 * endRange / proteinCount))
{
return(null);
}
for (int ii = i; ii < endRange; ii++)
{
var protein = new Protein(ProteomeDbPath, dbProteins[ii]);
proteinsList[ii] = protein;
}
Parallel.For(i, endRange, ii =>
{
var proteinSequences = new HashSet <string>(); // We only save the first dbDigestion.MaxSequenceLength characters of each peptide so collisions are likely
truncatedSequences[ii] = proteinSequences; // One hashset of sequences for each protein of interest
foreach (var digestedPeptide in protease.DigestSequence(proteinsList[ii].Sequence, maxMissedCleavages, null))
{
if (digestedPeptide.Sequence.Length < dbDigestion.MinSequenceLength)
{
continue;
}
var truncatedSequence = digestedPeptide.Sequence.Substring(
0, Math.Min(digestedPeptide.Sequence.Length, dbDigestion.MaxSequenceLength));
if (!existingSequences.Contains(truncatedSequence))
{
proteinSequences.Add(truncatedSequence);
}
}
});
}
// Now write to db
if (!UpdateProgressAndCheckForCancellation(progressMonitor, ref status, Resources.ProteomeDb_AddFastaFile_Saving_changes, 50))
{
return(null);
}
bool committed = true;
int digestedPeptideIdsCount;
try
{
using (var transaction = session.BeginTransaction())
{
session.SaveOrUpdate(dbDigestion);
Dictionary <String, long> digestedPeptideIds
= new Dictionary <string, long>();
const String sqlPeptide =
"INSERT INTO ProteomeDbDigestedPeptide (Digestion, Sequence) VALUES(?,?);select last_insert_rowid();"; // Not L10N
using (var commandPeptide = session.Connection.CreateCommand())
using (var commandProtein = session.Connection.CreateCommand())
{
commandPeptide.CommandText = sqlPeptide;
commandPeptide.Parameters.Add(new SQLiteParameter());
commandPeptide.Parameters.Add(new SQLiteParameter());
const String sqlPeptideProtein =
"INSERT INTO ProteomeDbDigestedPeptideProtein (Peptide, Protein) VALUES(?,?);"; // Not L10N
commandProtein.CommandText = sqlPeptideProtein;
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
for (int i = 0; i < proteinCount; i++)
{
var protein = proteinsList[i];
if (!UpdateProgressAndCheckForCancellation(progressMonitor, ref status, message, 50 * (proteinCount + i) / proteinCount))
{
return(null);
}
foreach (var truncatedSequence in truncatedSequences[i])
{
long digestedPeptideId;
if (!digestedPeptideIds.TryGetValue(truncatedSequence, out digestedPeptideId))
{
((SQLiteParameter)commandPeptide.Parameters[0]).Value = dbDigestion.Id;
((SQLiteParameter)commandPeptide.Parameters[1]).Value = truncatedSequence;
digestedPeptideId = Convert.ToInt64(commandPeptide.ExecuteScalar());
digestedPeptideIds.Add(truncatedSequence, digestedPeptideId);
}
((SQLiteParameter)commandProtein.Parameters[0]).Value = digestedPeptideId;
((SQLiteParameter)commandProtein.Parameters[1]).Value = protein.Id;
commandProtein.ExecuteNonQuery();
}
}
}
try
{
transaction.Commit();
}
catch (Exception)
{
committed = false;
}
digestedPeptideIdsCount = digestedPeptideIds.Count;
}
}
catch (Exception)
{
if (!committed)
{
return(null); // Interrupted
}
else
{
throw;
}
}
if (committed && !delayDbIndexing)
{
AnalyzeDb(session); // This runs asynchronously, and interferes with writes
}
if (committed)
{
progressMonitor.UpdateProgress(new ProgressStatus(string.Format(Resources.ProteomeDb_Digest_Digested__0__proteins_into__1__unique_peptides, proteinCount, digestedPeptideIdsCount)).ChangePercentComplete(100));
}
return(committed ? new Digestion(this, dbDigestion) : null);
}
}
public static void StartRamp(IProtease protease, double percentIdentifiedSteps = 0.05, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
List<Peptide> peps = new List<Peptide>();
List<Protein> proteins = new List<Protein>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
}
proteins.Add(protein);
}
}
// Fixed seed to make it reproducible
Random random = new Random(480912341);
peps = peps.OrderBy(x => random.Next()).ToList();
for (double percentIdentified = 0; percentIdentified <= 1; percentIdentified += percentIdentifiedSteps)
{
// Take the first x % to act as our identified peptides
List<Peptide> identifiedPeptides = peps.Take((int) (peps.Count*percentIdentified)).ToList();
List<ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
Console.WriteLine("{0} peptides {1} protein groups", identifiedPeptides.Count, proteinGroups.Count);
}
}
